---
# ------------------------------------------------------------------------------
# FILE: playbooks/day1_deploy_llm_inference.yml
# DESCRIPTION: Day 1 playbook for astro-orbiter LLM inference stack.
#              Deploys vLLM + Gemma 2 27B on RTX 3090 via OCuLink.
#
# Usage:
#   cd ~/git/homelab/ansible
#   ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference.yml
#
# Phases (added incrementally — safe to re-run):
#   1. Foundation  — groups, directories, vault assertion
#   2. Driver      — nvidia-driver-595-open (idempotent; already installed)
#   3. vLLM        — Python venv + pip install vllm
#   4. Model       — HF login, Gemma 2 27B snapshot_download
#   5. Serve       — systemd vllm-serve.service, health check
#   6. Integration — Hermes provider config on carousel
# ------------------------------------------------------------------------------

- name: Deploy LLM inference stack on astro-orbiter
  hosts: astro_orbiter
  gather_facts: true

  roles:
    - role: llm-inference